人工智能与储能技术融合的前沿发展

doi:10.19799/j.cnki.2095-4239.2024.0575

摘要/Abstract

摘要：

随着大规模储能系统和电气设备的不断适应，电池和超级电容器(supercapacitors)的储能能力面临着越来越多的需求和挑战。其中漫长的研发周期及低效率的材料筛选是储能材料(energy storage materials，ESM)开发的两大难题，将人工智能(artificial Intelligence，AI)应用于ESM的研发是解决该问题的新方案。而机器学习(machine Learning，ML)作为AI的子领域，已被证明是从数据中获得见解的强大工具，ML可以挖掘大数据背后有价值的信息和隐含的关联，有助于揭示ESM的关键结构或性质与性能关系，大大加快了ESM的研发和筛选，同时AI为储能系统的设计和运行提供了先进的预测工具。因此，未来AI与储能技术的融合研究将是值得关注的新兴领域。本文首先阐述了AI的关键技术框架，包括监督学习、无监督学习以及可解释的人工智能(XAI)。然后从ESM设计、识别筛选和性能预测三个方向出发，分别总结了AI在这些储能领域的最新研究进展，包括机器学习在储能材料研究中常用的数据库列表，并分析了这一融合技术对智能电网优化、可再生能源集成与管理的贡献。最后，本文展望了AI与储能技术的融合面临的机遇挑战，以及未来需要重点关注的研究方向。

关键词: 人工智能, 储能, 融合, 智能电网, 可再生能源

Abstract:

With the continuous adaptation of large-scale energy storage systems and electrical equipment, the energy storage capacity of batteries and supercapacitors is facing increasing demands and challenges. The long research and development cycle and inefficient material screening are two major problems in the development of energy storage materials (ESM). The application of artificial intelligence (AI) to ESM is a new solution to this problem. Furthermore, machine learning (ML), an aspect of AI, has proven to be a powerful tool to for gaining insights from data. ML can mine data behind valuable information and implicit correlation, help to reveal the key structure of ESM or properties and performance relationships, and significantly accelerate ESM development and screening. At the same time, AI for energy storage system design and operation provides advanced prediction tools. Therefore, future integration research on AI and energy storage technology will be an emerging field worthy of attention. This study first provides an overview of the key technical framework for AI, including the ML process, supervised and unsupervised learning, and explainable AI. Then, the latest research progress of AI in ESM design, identification, screening, and performance prediction is summarized. A list of databases commonly used in ML in energy storage materials research is also provided. The contribution of this fusion technology to smart grid optimization and renewable energy integration and management is briefly analyzed. Finally, this study looks at the opportunities and challenges facing the integration of AI and energy storage technology, as well as the research directions to focus on in the future.

Key words: artificial intelligence, energy storage, fusion, smart grid, renewable energy

中图分类号:

TK 02

黄家辉, 邝祝芳. 人工智能与储能技术融合的前沿发展[J]. 储能科学与技术, 2024, 13(9): 3161-3181.

Jiahui HUANG, Zhufang KUANG. The forefront of the integration of artificial intelligence and energy storage technologies[J]. Energy Storage Science and Technology, 2024, 13(9): 3161-3181.

图/表 8

图1

表1

表2

表3

图2

表4

机器学习用于电池技术中常见的数据库汇总"

数据集	提供的信息	URL
CALCE	锂离子电池在不同温度、倍率等条件下的循环充放电电化学数据	https://calce.umd.edu
NASA	多种操作条件下多种类型锂离子电池的充电和放电电池数据	https://www.nasa.gov/
Oxford Battery Degradation Dataset 1	8个Kokam(SLPB533459H4)740 mAh锂离子袋电池的长期电池老化试验，测量数据包括电流、电压、容量、RPT试验和EIS试验等	https://howey.eng.ox.ac.uk/dataand-code/
TRI	快速充电协议下的磷酸石墨商用锂离子电池标称容量为1.1 Ah、标称电压为3.3 V的商用锂离子蓄电池，由124个在快速充电条件下循环失效的电池组成	https://data.matr.io/1/
Material Project	包括无机材料、纳米材料、热力学数据、相图、电池材料等，易于操作和可搜索的材料物理性质等	https://materialsproject.org/
PolyInfo	各文献中收集的聚合物名称、化学结构、物理性能、测量条件、聚合方法、成型方法、原料单体等信息	https://polymer.nims.go.jp/
SuperCon	从科学技术文献中提取的无机和有机材料的超导性及其相关特性	https://dice.nims.go.jp/news/2021/12/20211221.html
AtomWork	从科技文献中提取的无机材料的晶体结构、X射线衍射、性质和相图信息	https://crystdb.nims.go.jp/en/
AFLOW	一个包含数百万种材料化合物和计算性质的全球可用数据库，除了提供有关晶体能带、热性能和机械性能的信息外，还特别有用，可以作为研究晶体对称性的指南	http://aflowlib.org/
Open Quantum Materials Dataset	开放量子材料数据库是一个基于DFT计算的材料热力学和结构信息数据库，包括材料的热力学和结构数据	https://oqmd.org/
ChemSpider	化学结构	http://www.chemspider.com
CMR	支持许多电子结构模拟器产生的数据的收集、存储、检索、分析和共享的基础设施	https://cmr.fysik.dtu.dk
COD	有机、无机、金属有机化合物和矿物的结构，不包括生物聚合物	http://crystallography.net/cod
CSD	小分子晶体结构	https://www.ccdc.cam.ac.uk
HTEM	薄膜的特性	https://htem.nrel.gov
ICSD	无机晶体结构数据库	https://icsd.fiz-karlsruhe.de
Khazana	结构和性能，通过从数据中学习来设计材料的工具	https://khazana.gatech.edu
MatNavl	聚合物和无机材料的晶体结构、电子结构、性能和相图	https://mits.nims.go.jp
NOMAD	用户驱动的计算材料科学数据共享和开发平台	https://nomad-coe.eu
NREL Materials Dataset	可再生能源应用材料的特性	https://materials.nrel.gov
Organic Materials Dataset	三维有机晶体电子结构数据库	https://omdb.mathub.io
ZINC	市售分子的2D和3D结构	https://zinc15.docking.org

表4

表5

ML应用于储能材料的研究进展"

研究方向	ML方法	主要研究内容
辅助储能材料的设计	基于隐式/显式特征的高效ML方法	通过特征重要性排序来确定关键的容量影响因素，便于有效的容量估计和制定高容量组件^[13]
	岭和套索回归，线性回归，SVM，ANN	具有非常规特征的岭回归方法在所有情况中效果最好^[17]
	基于优化遗传算法的区间支持向量回归预测器(OGA-ISVR)	确定了特征与属性以及影响介电常数的因素之间的映射关系，实现了聚合物介电设计中的即时性能预测^[18]
	DNN	该模型允许分子在离散表示和多维连续表示之间来回切换^[19]
	机器学习协议	加快基于DFT计算得到的主要局部能量最小值的系统映射，然后快速筛选多硫化锂在单原子催化剂上的吸附特性^[20]
	基于机器学习增强技术的高通量钙钛矿薄膜的制造与优化研究	仅使用具有一系列不同组件的钙钛矿薄膜，这些太阳能电池的性能和表征数据被用于训练一个ML模型，可以优化材料参数，并指导改进材料的设计^[21]

识别	布谷鸟搜索算法 (模型参数标识)	提出了一种数据驱动的参数识别框架，仅输入电流和电压数据进行多目标全局优化，进一步解决了使用有限电池数据时的过拟合问题^[24]
	布谷鸟搜索算法 (退化模式识别)	利用实时现场数据和机器学习技术提高了对电池状态的理解和预测，即使在传感器噪声条件下，该方法在老化参数估计和退化模态识别方面仍显示出较高的精度和鲁棒性^[25]
	ANN, 遗传算法	更全面地考虑地质结构、运行参数和性能指标之间的复杂关系，以协助选择性能为最好的高温蓄热系统选址^[26]

分类	深度学习	快速、自动地分类和量化电池的老化模式^[27]
分类	决策树，梯度增强	低复杂度机器学习模块对低信噪比的原始数据进行分类，实时精度超过95.8%，功耗仅为53 mW^[28]

筛选	人工智能驱动的框架	预测相应电池的开路电压，并对材料的氧化还原稳定性进行初步评估^[29]
	人工智能、量子力学	加快发现适合于有机电极材料的阴极活性物质，准确识别导致更高电压电极的常见分子官能团，并表明一种有趣的供体-受体效应^[30]
	组合搜索空间大小	增加无铅BaTiO₃基介质在低电场下的储能密度^[31]
	ML,GCNN,DFT	有效寻找具有高热容的潜在材料^[32]
	ML和遗传算法	加速了在高温和高电场下可使用的新型聚合物的发现和设计^[33]
	晶体学图卷积神经网络	可充电锌电池中高容量、高电压阴极材料的筛选^[35]

性能预测	CNN	预测电池在充满电和完全放电状态下的阻抗谱，在充电数据为不完整的情况下仍能提供可靠的预测^[41]
	多任务学习	可以预测容量和内阻的退化轨迹，包括拐点和寿命终点^[42]
	RNN	将RUL预测扩展到固定和随机未来操作条件下的充放电容量轨迹的预测^[43]
	LSTM	将LSTM与现有的SOC估计方法(经验方法、库尔布计数方法、扩展卡尔曼滤波、无跟踪卡尔曼滤波)和前馈神经网络的性能进行了比较。LSTM网络在MAE和RMSE方面表现良好
	ML,分子模拟	对6种ML算法进行了评估，结果表明，预测的热导率空间分别为0.995和0.991^[49]。
	ANN,多层感知器模型(MLP)	人工神经网络模型准确预测了达到预先指定的熔体分数所需的时间^[50]
	神经网络，SVM，逻辑回归，随机森林	预测并调度住宅光伏/电池系统下一个运行间隔的实时运行模式，减少本地控制器的计算负担^[54]

表5

图3

参考文献 70

1	YAO Z P, LUM Y, JOHNSTON A, et al. Machine learning for a sustainable energy future[J]. Nature Reviews Materials, 2023, 8(3): 202-215. DOI: 10.1038/s41578-022-00490-5.
2	MILIDONIS K, BLANCO M J, GRIGORIEV V, et al. Review of application of AI techniques to solar tower systems[J]. Solar Energy, 2021, 224: 500-515. DOI: 10.1016/j.solener.2021.06.009.
3	YANG H, HE Z Q, ZHANG M D, et al. Reshaping the material research paradigm of electrochemical energy storage and conversion by machine learning[J]. EcoMat, 2023, 5(5): e12330. DOI: 10.1002/eom2.12330.
4	TCHUENTE D, LONLAC J, KAMSU-FOGUEM B. A methodological and theoretical framework for implementing explainable artificial intelligence (XAI) in business applications[J]. Computers in Industry, 2024, 155: 104044. DOI: 10.1016/j.compind.2023.104044.
5	ZHU Y H, WU X F, GOTAWALA N, et al. Thermal prediction of additive friction stir deposition through Bayesian learning-enabled explainable artificial intelligence[J]. Journal of Manufacturing Systems, 2024, 72: 1-15. DOI: 10.1016/j.jmsy.2023.10.015.
6	XIA H S, HOU X Y, ZHANG J Z P. Long- and short-term memory model of cotton price index volatility risk based on explainable artificial intelligence[J]. Big Data, 2024, 12(1): 49-62. DOI: 10.1089/big.2022.0287.
7	THUNOLD H, RIEGLER M, YAZIDI A, et al. A deep diagnostic framework using explainable artificial intelligence and clustering[J]. Diagnostics, 2023, 13(22): 3413. DOI: 10.3390/diagnostics13223413.
8	AHMAD WANI N, KUMAR R, BEDI J. DeepXplainer: An interpretable deep learning based approach for lung cancer detection using explainable artificial intelligence[J]. Computer Methods and Programs in Biomedicine, 2024, 243: 107879. DOI: 10.1016/j.cmpb.2023.107879.
9	CHAKRABORTY S, TALUKDER M B U, HASAN M M, et al. BiGRU-ANN based hybrid architecture for intensified classification tasks with explainable AI[J]. International Journal of Information Technology, 2023, 15(8): 4211-4221. DOI: 10.1007/s41870-023-01515-0.
10	IBRAHIM S M, ANSARI S S, HASAN S D. Towards white box modeling of compressive strength of sustainable ternary cement concrete using explainable artificial intelligence (XAI)[J]. Applied Soft Computing, 2023, 149: 110997. DOI: 10.1016/j.asoc.2023.110997.
11	LIU X Y, PENG H J, LI B Q, et al. Untangling degradation chemistries of lithium-sulfur batteries through interpretable hybrid machine learning[J]. Angewandte Chemie International Edition, 2022, 61(48): e202214037. DOI: 10.1002/anie.202214037.
12	BARRETT D H, HARUNA A. Artificial intelligence and machine learning for targeted energy storage solutions[J]. Current Opinion in Electrochemistry, 2020, 21: 160-166. DOI: 10.1016/j.coelec.2020.02.002.
13	ZHOU P P, XIAO X Z, ZHU X Y, et al. Machine learning enabled customization of performance-oriented hydrogen storage materials for fuel cell systems[J]. Energy Storage Materials, 2023, 63: 102964. DOI: 10.1016/j.ensm.2023.102964.
14	FARAJI NIRI M, REYNOLDS C, ROMÁN RAMÍREZ L A, et al. Systematic analysis of the impact of slurry coating on manufacture of Li-ion battery electrodes via explainable machine learning[J]. Energy Storage Materials, 2022, 51: 223-238. DOI: 10.1016/j.ensm.2022.06.036.
15	FENG Y, TANG W X, ZHANG Y, et al. Machine learning and microstructure design of polymer nanocomposites for energy storage application[J]. High Voltage, 2022, 7(2): 242-250. DOI: 10.1049/hve2.12152.
16	LI S C, BARNARD A S. Inverse design of MXenes for high-capacity energy storage materials using multi-target machine learning[J]. Chemistry of Materials, 2022, 34(11): 4964-4974. DOI: 10.1021/acs.chemmater.2c00200.
17	HASAN A S M J, YUSUF J, FARUQUE R B. Performance comparison of machine learning methods with distinct features to estimate battery SOC[C]// 2019 IEEE Green Energy and Smart Systems Conference (IGESSC). IEEE, 2019: 1-5. DOI: 10.1109/IGESSC47875.2019.9042399.
18	YI Y, WANG L M, CHEN Z Y. Adaptive global kernel interval SVR-based machine learning for accelerated dielectric constant prediction of polymer-based dielectric energy storage[J]. Renewable Energy, 2021, 176: 81-88. DOI: 10.1016/j.renene. 2021.05.045.
19	GÓMEZ-BOMBARELLI R, WEI J N, DUVENAUD D, et al. Automatic chemical design using a data-driven continuous representation of molecules[J]. ACS Central Science, 2018, 4(2): 268-276. DOI: 10.1021/acscentsci.7b00572.
20	ANDRITSOS E I, ROSSI K. Accelerating the theoretical study of Li-polysulfide adsorption on single-atom catalysts via machine learning approaches[J]. International Journal of Quantum Chemistry, 2022, 122(17): e26956. DOI: 10.1002/qua.26956.
21	MEFTAHI N, SURMIAK M A, FÜRER S O, et al. Machine learning enhanced high-throughput fabrication and optimization of quasi-2D ruddlesden-popper perovskite solar cells[J]. Advanced Energy Materials, 2023, 13(38): 2203859. DOI: 10.1002/aenm.202203859.
22	ZHENG L, ZHANG S Q, HUANG H, et al. Artificial intelligence-driven rechargeable batteries in multiple fields of development and application towards energy storage[J]. Journal of Energy Storage, 2023, 73: 108926. DOI: 10.1016/j.est.2023.108926.
23	CHEN H H, ZHENG Y Z, LI J L, et al. AI for nanomaterials development in clean energy and carbon capture, utilization and storage (CCUS)[J]. ACS Nano, 2023, 17(11): 9763-9792. DOI: 10.1021/acsnano.3c01062.
24	LI W H, DEMIR I, CAO D C, et al. Data-driven systematic parameter identification of an electrochemical model for lithium-ion batteries with artificial intelligence[J]. Energy Storage Materials, 2022, 44: 557-570. DOI: 10.1016/j.ensm.2021.10.023.
25	LI W H, CHEN J, QUADE K, et al. Battery degradation diagnosis with field data, impedance-based modeling and artificial intelligence[J]. Energy Storage Materials, 2022, 53: 391-403. DOI: 10.1016/j.ensm.2022.08.021.
26	JIN W C, ATKINSON T A, DOUGHTY C, et al. Machine-learning-assisted high-temperature reservoir thermal energy storage optimization[J]. Renewable Energy, 2022, 197: 384-397. DOI: 10.1016/j.renene.2022.07.118.
27	KIM S, YI Z G, CHEN B R, et al. Rapid failure mode classification and quantification in batteries: A deep learning modeling framework[J]. Energy Storage Materials, 2022, 45: 1002-1011. DOI: 10.1016/j.ensm.2021.07.016.
28	XU J C, CHEN E, CHEN V. Energy-efficient data symbol detection via boosted learning for multi-actuator data storage systems[C]// 2021 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 2021: 1-5. DOI: 10.1109/ISCAS 51556.2021.9401676.
29	CARVALHO R P, BRANDELL D, ARAUJO C M. An evolutionary-driven AI model discovering redox-stable organic electrode materials for alkali-ion batteries[J]. Energy Storage Materials, 2023, 61: 102865. DOI: 10.1016/j.ensm.2023.102865.
30	CARVALHO R P, MARCHIORI C F N, BRANDELL D, et al. Artificial intelligence driven in-silico discovery of novel organic lithium-ion battery cathodes[J]. Energy Storage Materials, 2022, 44: 313-325. DOI: 10.1016/j.ensm.2021.10.029.
31	YUAN R H, TIAN Y, XUE D Z, et al. Accelerated search for BaTiO₃-based ceramics with large energy storage at low fields using machine learning and experimental design[J]. Advanced Science, 2019, 6(21): 1901395. DOI: 10.1002/advs.201901395.
32	OJIH J, ONYEKPE U, RODRIGUEZ A, et al. Machine learning accelerated discovery of promising thermal energy storage materials with high heat capacity[J]. ACS Applied Materials & Interfaces, 2022, 14(38): 43277-43289. DOI: 10.1021/acsami. 2c11350.
33	KERN J, CHEN L H, KIM C, et al. Design of polymers for energy storage capacitors using machine learning and evolutionary algorithms[J]. Journal of Materials Science, 2021, 56(35): 19623-19635. DOI: 10.1007/s10853-021-06520-x.
34	ZHAO L N, CHANG Y, QIU S, et al. High mechanical energy storage capacity of ultranarrow carbon nanowires bundles by machine learning driving predictions[J]. Advanced Energy and Sustainability Research, 2023, 4(11): 2300112. DOI: 10.1002/aesr.202300112.
35	ZHOU L M, YAO A M, WU Y J, et al. Machine learning assisted prediction of cathode materials for Zn-ion batteries[J]. Advanced Theory and Simulations, 2021, 4(9): 2100196. DOI: 10.1002/adts.202100196.
36	LUO Z Y, YANG X Y, WANG Y X, et al. A survey of artificial intelligence techniques applied in energy storage materials R&D[J]. Frontiers in Energy Research, 2020, 8: 116. DOI: 10.3389/fenrg.2020.00116.
37	ZHANG Y Z, ZHAO M Y. Cloud-based in situ battery life prediction and classification using machine learning[J]. Energy Storage Materials, 2023, 57: 346-359. DOI: 10.1016/j.ensm. 2023.02.035.
38	ZHANG H K, WANG Z L, REN J H, et al. Ultra-fast and accurate binding energy prediction of shuttle effect-suppressive sulfur hosts for lithium-sulfur batteries using machine learning[J]. Energy Storage Materials, 2021, 35: 88-98. DOI: 10.1016/j.ensm.2020.11.009.
39	GHOSH S, RAO G R, THOMAS T. Machine learning-based prediction of supercapacitor performance for a novel electrode material: Cerium oxynitride[J]. Energy Storage Materials, 2021, 40: 426-438. DOI: 10.1016/j.ensm.2021.05.024.
40	XIONG R, SUN Y, WANG C X, et al. A data-driven method for extracting aging features to accurately predict the battery health[J]. Energy Storage Materials, 2023, 57: 460-470. DOI: 10.1016/j.ensm.2023.02.034.
41	DUAN Y Z, TIAN J P, LU J H, et al. Deep neural network battery impedance spectra prediction by only using constant-current curve[J]. Energy Storage Materials, 2021, 41: 24-31. DOI: 10.1016/j.ensm.2021.05.047.
42	LI W H, ZHANG H T, VAN VLIJMEN B, et al. Forecasting battery capacity and power degradation with multi-task learning[J]. Energy Storage Materials, 2022, 53: 453-466. DOI: 10.1016/j.ensm.2022.09.013.
43	LU J H, XIONG R, TIAN J P, et al. Battery degradation prediction against uncertain future conditions with recurrent neural network enabled deep learning[J]. Energy Storage Materials, 2022, 50: 139-151. DOI: 10.1016/j.ensm.2022.05.007.
44	TIAN J P, XIONG R, SHEN W X, et al. Flexible battery state of health and state of charge estimation using partial charging data and deep learning[J]. Energy Storage Materials, 2022, 51: 372-381. DOI: 10.1016/j.ensm.2022.06.053.
45	ZAHID T, XU K, LI W M. Machine learning an alternate technique to estimate the state of charge of energy storage devices[J]. Electronics Letters, 2017, 53(25): 1665-1666. DOI: 10.1049/el.2017.2677.
46	YUE D, FENG Y, LIU X X, et al. Prediction of energy storage performance in polymer composites using high-throughput stochastic breakdown simulation and machine learning[J]. Advanced Science, 2022, 9(17): e2105773. DOI: 10.1002/advs.202105773.
47	ILIADIS P, NTOMALIS S, ATSONIOS K, et al. Energy management and techno-economic assessment of a predictive battery storage system applying a load levelling operational strategy in island systems[J]. International Journal of Energy Research, 2021, 45(2): 2709-2727. DOI: 10.1002/er.5963.
48	DING S C, LI Y D, DAI H F, et al. Accurate model parameter identification to boost precise aging prediction of lithium-ion batteries: A review[J]. Advanced Energy Materials, 2023, 13(39): 2301452. DOI: 10.1002/aenm.202301452.
49	LEMAOUI T, DARWISH A S, ALMUSTAFA G, et al. Machine learning approach to map the thermal conductivity of over 2, 000 neoteric solvents for green energy storage applications[J]. Energy Storage Materials, 2023, 59: 102795. DOI: 10.1016/j.ensm.2023.102795.
50	REN G, CHUTTAR A, BANERJEE D. Exploring efficacy of machine learning (artificial neural networks) for enhancing reliability of thermal energy storage platforms utilizing phase change materials[J]. International Journal of Heat and Mass Transfer, 2022, 189: 122628. DOI: 10.1016/j.ijheatmasstransfer.2022.122628.
51	TASNEEM S, SULTAN H S, ALI AGEELI A, et al. Machine learning modeling of reversible thermochemical reactions applicable in energy storage systems[J]. Journal of the Taiwan Institute of Chemical Engineers, 2023, 148: 104926. DOI: 10.1016/j.jtice.2023.104926.
52	ALDEN R E, JONES E S, POORE S B, et al. Digital twin for HVAC load and energy storage based on a hybrid ML model with CTA-2045 controls capability[C]// 2022 IEEE Energy Conversion Congress and Exposition (ECCE). IEEE, 2022: 1-5. DOI: 10.1109/ECCE50734.2022.9948141.
53	SYED M A, KHALID M. Machine learning based controlled filtering for solar PV variability reduction with BESS[C]// 2021 International Conference on Sustainable Energy and Future Electric Transportation (SEFET). IEEE, 2021: 1-5. DOI: 10.1109/SeFet48154.2021.9375792.
54	HENRI G, LU N. A supervised machine learning approach to control energy storage devices[C]// 2020 IEEE Power & Energy Society General Meeting (PESGM). IEEE, 2020: 1. DOI: 10.1109/PESGM41954.2020.9281748.
55	LIU F, LIU Q Y, TAO Q, et al. Deep reinforcement learning based energy storage management strategy considering prediction intervals of wind power[J]. International Journal of Electrical Power & Energy Systems, 2023, 145: 108608. DOI: 10.1016/j.ijepes.2022.108608.
56	WIJESINGHA J R, HASANTHI B V D R, WIJEGUNASINGHE I P D, et al. Smart residential energy management system (REMS) using machine learning[C]// 2021 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE). IEEE, 2021: 90-95. DOI: 10.1109/ICCIKE51210.2021.9410779.
57	JAIN M, SUN X Q, DATTA S, et al. A machine learning framework to deconstruct the primary drivers for electricity market price events[C]// 2023 IEEE Power & Energy Society General Meeting (PESGM). IEEE, 2023: 1-5. DOI: 10.1109/PESGM52003. 2023.10252752.
58	SIVAKUMAR P, PRASAD P A, KALEESWARI M, et al. Machine learning-based LFC modelling for solar and wind power plant[C]// 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE, 2023: 174-180. DOI: 10.1109/ICESC57686.2023.10193006.
59	KHOSHLESSAN M, FAHIMI B, KIANI M. A comparison between Machine learning algorithms for the application of micro-grids Energy management[C]// 2020 IEEE International Conference on Industrial Technology (ICIT). IEEE, 2020: 805-809. DOI: 10.1109/ICIT45562.2020.9067203.
60	SHEHA M, POWELL K. Using real-time electricity prices to leverage electrical energy storage and flexible loads in a smart grid environment utilizing machine learning techniques[J]. Processes, 2019, 7(12): 870. DOI: 10.3390/pr7120870.
61	MOHAPATRA P, VENKATA RAMANA NAIK N, PANDA A K. Machine learning-based SoC estimation: A recent advancement in battery energy storage system[J]. Energy Storage Technologies in Grid Modernization, 2023: 159-179.
62	DONTI P L, KOLTER J Z. Machine learning for sustainable energy systems[J]. Annual Review of Environment and Resources, 2021, 46: 719-747. DOI: 10.1146/annurev-environ-020220-061831.
63	SHIBL M M, ISMAIL L S, MASSOUD A M. An intelligent two-stage energy dispatch management system for hybrid power plants: Impact of machine learning deployment[J]. IEEE Access, 2023, 11: 13091-13102. DOI: 10.1109/ACCESS.2023.3243097.
64	KAMALAKANNAN J, REDDY K R, KUMAR N, et al. Design of hybrid energy storage and management system in hybrid electric vehicle using machine learning approach[C]// 2023 4th International Conference on Smart Electronics and Communication (ICOSEC). IEEE, 2023: 1313-1317. DOI: 10.1109/ICOSEC58147.2023.10276076.
65	ABARNA S, GOWSALYA K, RAVINDRAN M, et al. Optimal cost and energy scheduling of polyphase energy management system-machine learning approach[C]// 2022 6th International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE, 2022: 1404-1408. DOI: 10.1109/ICICCS53718. 2022.9788352.
66	LIN Y Q, LI B H, MOISER T M, et al. Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques[J]. Journal of Energy Storage, 2022, 50: 104123. DOI: 10.1016/j.est.2022.104123.
67	LEE S, CHOI D H. Reinforcement learning-based energy management of smart home with rooftop solar photovoltaic system, energy storage system, and home appliances[J]. Sensors, 2019, 19(18): 3937. DOI: 10.3390/s19183937.
68	KEYNIA F, MEMARZADEH G. A new financial loss/gain wind power forecasting method based on deep machine learning algorithm by using energy storage system[J]. IET Generation, Transmission & Distribution, 2022, 16(5): 851-868. DOI: 10.1049/gtd2.12332.
69	PATTANAIK S S, SAHOO A K, PANDA R, et al. Optimal power allocation of battery energy storage system (BESS) using dense LSTM in active distribution network[J]. Energy Storage, 2024, 6(1). DOI: 10.1002/est2.529.
70	YAVASOGLU H A, TETIK Y E, OZCAN H G. Neural network-based energy management of multi-source (battery/UC/FC) powered electric vehicle[J]. International Journal of Energy Research, 2020, 44(15): 12416-12429. DOI: 10.1002/er.5429.

类别	具体算法
线性模型	线性回归、逻辑回归
非线性分类模型	K近邻算法(KNN)
基于核函数的模型	支持向量机(SVM)
决策树	随机森林(RF)、梯度提升决策树
神经网络和深度学习	人工神经网络(ANN)、卷积神经网络(CNN)、递归神经网络(RNN)及其变种模型。
概率模型	贝叶斯网络(Bayes)

分类	方法	模型	策略	算法
二类分类	感知机	分离超平面	极小化误分点到超平面距离	随机梯度下降
多类分类，回归	K近邻法	特征空间，样本点
多类分类	朴素贝叶斯法	特征与类别的联合概率分布，条件独立假设	极大似然估计，最大后验概率估计	概率计算公式，EM算法
多类分类，回归	决策树	判别模型	正则化的极大似然估计	特征选择，生成，剪枝
二类分类	支持向量机	分离超平面，核技巧	极小化正则化合页损失，软间隔最大化	序列最小最优化算法
二类分类	提升方法	弱分类器的线性组合	极小化加法模型的指数损失	前向分布加法算法
概率模型参数估计	EM算法	含隐变量概率模型	极大似然估计，最大后验概率估计	迭代算法

分类	方法	模型	策略	算法
聚类	层次聚类	聚类树	类内样本距离最小	启发式算法
	k均值聚类	k中心聚类	样本与类中心距离最小	迭代算法
	高斯混合模型	高斯混合模型	似然函数最大	EM算法
降维	PCA	低维正交空间	方差最大	SVD
话题分析	LSA	矩阵分解模型	平方损失最小	SVD
	NMF	矩阵分解模型	平方损失最小	非负矩阵分解
	PLSA	PLSA模型	似然函数最大	EM算法
	LDA	LDA模型	后验概率估计	吉布斯抽样，变分推理
图分析	PageRank	有向图上的马尔可夫链	平稳分布求解	幂法

[1]	袁誉杭, 高宇辰, 张俊东, 高岩斌, 王超珑, 陈翔, 张强. 大语言模型在储能研究中的应用[J]. 储能科学与技术, 2024, 13(9): 2907-2919.
[2]	刘大猛, 牟雪鹏, 石博豪, 陈巨龙, 王斌, 罗晨, 钟承君, 陈思哲. 斜坡式重力储能系统机械与电气联合仿真的多软件协同建模方法[J]. 储能科学与技术, 2024, 13(9): 3266-3276.
[3]	焦君宇, 张全權, 陈宁波, 王冀钰, 芦秋迪, 丁浩浩, 彭鹏, 宋孝河, 张帆, 郑家新. 电池大数据智能分析平台的研发与应用[J]. 储能科学与技术, 2024, 13(9): 3198-3213.
[4]	许晶, 王宇琦, 符晓, 杨其凡, 连景臣, 王力奇, 肖睿娟. 基于大数据的电池新材料设计[J]. 储能科学与技术, 2024, 13(9): 2920-2932.
[5]	刘子玉, 姜泽坤, 邱伟, 徐泉, 牛迎春, 徐春明, 周天航. 人工智能在长时液流电池储能中的应用：性能优化和大模型[J]. 储能科学与技术, 2024, 13(9): 2871-2883.
[6]	邓斌, 华海明, 张与之, 王晓旭, 张林峰. 深度势能方法及其在电化学储能材料中的应用[J]. 储能科学与技术, 2024, 13(9): 2884-2906.
[7]	李清波, 张懋慧, 罗英, 吕桃林, 解晶莹. 基于等效电路模型融合电化学原理的锂离子电池荷电状态估计[J]. 储能科学与技术, 2024, 13(9): 3072-3083.
[8]	栗占伟, 樊东方, 曾超, 何雯倩, 何金. 考虑风光消纳的储能系统容量优化配置及运行策略研究[J]. 储能科学与技术, 2024, 13(8): 2713-2725.
[9]	李玉光, 刘翔, 梁艳召, 刘双振. 飞轮储能装置在轨道交通中的应用研究[J]. 储能科学与技术, 2024, 13(8): 2679-2686.
[10]	周茜茜, 黄勇, 崔可, 孙大南. 飞轮储能装置电机温度场仿真技术研究及试验验证[J]. 储能科学与技术, 2024, 13(8): 2589-2596.
[11]	陈晔, 李晋, 吴候福, 张少禹, 储玉喜, 卓萍. 大容量储能电池模组热失控传播行为与燃爆风险分析[J]. 储能科学与技术, 2024, 13(8): 2803-2812.
[12]	柳长发, 付立衡, 张增丽, 李宏胜, 古敬彬. 高比例光伏接入的分布式储能容量自适应协调控制方法[J]. 储能科学与技术, 2024, 13(8): 2696-2703.
[13]	李澎煜, 林曦鹏, 王亮, 陈海生, 王艺斐. 竖直波纹流道内超临界氮气流动与传热研究[J]. 储能科学与技术, 2024, 13(8): 2605-2614.
[14]	李震, 陈巨龙, 李文林, 张裕, 杨婕睿, 陈思哲. 提升斜坡式重力储能AGC性能的混合储能优化运行方法[J]. 储能科学与技术, 2024, 13(8): 2761-2771.
[15]	李永奇, 杜蕴, 方振华, 张松通, 祝夏雨, 胡海良, 邱景义, 明海. 军用新能源微电网系统的运维及故障处置分析[J]. 储能科学与技术, 2024, 13(8): 2740-2757.